{"id":"W4352976756","doi":"10.1007/978-3-031-28719-0_24","title":"Value Cores for Inner and Outer Alignment: Simulating Personality Formation via Iterated Policy Selection and Preference Learning with Self-World Modeling Active Inference Agents","year":2023,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Decision-Making and Behavioral Economics","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Iterated function; Selection (genetic algorithm); Inference; Preference; Value (mathematics); Artificial intelligence; Computer science; Personality; Machine learning; Psychology; Mathematics; Statistics; Social psychology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001453229,0.0003339231,0.0007373351,0.0004166273,0.0007340274,0.001152091,0.001182418,0.001512196,0.00376018],"category_scores_gemma":[0.01024594,0.0005209615,0.0005746037,0.0004013739,0.001208422,0.001542645,0.001111694,0.001606776,0.0002682469],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001309214,"about_ca_system_score_gemma":0.001004143,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01252785,"about_ca_topic_score_gemma":0.00911055,"domain_scores_codex":[0.9997012,0.000157313,0.000008037103,0.00004029185,0.00002887762,0.00006439012],"domain_scores_gemma":[0.9950166,0.003866649,0.0002319328,0.000241696,0.0002375894,0.0004055938],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001865313,0.0001449274,0.00230046,0.00002091588,0.00002867247,0.00006448797,0.0001859617,0.9636,0.0004599134,0.02631783,0.0007818058,0.005908478],"study_design_scores_gemma":[0.00000884365,0.000005711262,0.00008572537,0.000001094996,0.000001485775,0.000001510138,0.000008527059,0.9971527,0.00005382734,0.002655444,0.00002327555,0.000001925891],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8541502,0.0001165934,0.1373054,0.0007132723,0.00009070485,0.00005251146,0.0001365128,0.000184648,0.007250228],"genre_scores_gemma":[0.9844492,0.00002185878,0.01375401,0.00005608344,0.00001049062,0.0000373406,0.0000482378,0.00003283909,0.001589919],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01252785,"threshold_uncertainty_score":0.02490985,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2426187814753632,"score_gpt":0.4146930962041733,"score_spread":0.1720743147288102,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}